{"id":58201,"date":"2025-02-19T17:32:00","date_gmt":"2025-02-19T17:32:00","guid":{"rendered":"http:\/\/574d70a3-6756-4b36-8486-e0d863da2c9b"},"modified":"2025-02-19T17:32:00","modified_gmt":"2025-02-19T17:32:00","slug":"yikes-jailbroken-grok-3-can-be-made-to-say-and-reveal-just-about-anything","status":"publish","type":"post","link":"https:\/\/www.threatshub.org\/blog\/yikes-jailbroken-grok-3-can-be-made-to-say-and-reveal-just-about-anything\/","title":{"rendered":"Yikes: Jailbroken Grok 3 can be made to say and reveal just about anything"},"content":{"rendered":"<figure class=\"c-shortcodeImage u-clearfix c-shortcodeImage-large\">\n<div class=\"c-shortcodeImage_imageContainer\">\n<div class=\"c-shortcodeImage_image\"><picture class=\"c-cmsImage c-cmsImage_loaded\"><source media=\"(max-width: 767px)\" srcset=\"https:\/\/www.zdnet.com\/a\/img\/resize\/32f1ab074f68f864ad325a887dc04b2b1bcf1cf6\/2025\/02\/19\/bedbbafb-fcc1-43f7-a9e2-e0ab710f2a45\/gettyimages-1741475260.jpg?auto=webp&amp;width=768\" alt=\"gettyimages-1741475260\"><source media=\"(max-width: 1023px)\" srcset=\"https:\/\/www.zdnet.com\/a\/img\/resize\/6e962361dda23d26d0e5b9ca19f19233cc1caadf\/2025\/02\/19\/bedbbafb-fcc1-43f7-a9e2-e0ab710f2a45\/gettyimages-1741475260.jpg?auto=webp&amp;width=1024\" alt=\"gettyimages-1741475260\"><source media=\"(max-width: 1440px)\" srcset=\"https:\/\/www.zdnet.com\/a\/img\/resize\/fb47548cd0afa75df9d0835c03d9d6c0e9ec9d0c\/2025\/02\/19\/bedbbafb-fcc1-43f7-a9e2-e0ab710f2a45\/gettyimages-1741475260.jpg?auto=webp&amp;width=1280\" alt=\"gettyimages-1741475260\"><img decoding=\"async\" src=\"https:\/\/www.zdnet.com\/a\/img\/resize\/fb47548cd0afa75df9d0835c03d9d6c0e9ec9d0c\/2025\/02\/19\/bedbbafb-fcc1-43f7-a9e2-e0ab710f2a45\/gettyimages-1741475260.jpg?auto=webp&amp;width=1280\" alt=\"gettyimages-1741475260\" width=\"1280\" height=\"853.3333333333333\" fetchpriority=\"low\"><\/picture><\/div>\n<p> <!----><\/div><figcaption> <span class=\"c-shortcodeImage_credit g-outer-spacing-top-xsmall u-block\">J Studios\/Getty Images<\/span><\/figcaption><\/figure>\n<p>Just a day after its release, xAI&#8217;s latest model,&nbsp;<a href=\"https:\/\/www.zdnet.com\/article\/xais-grok-3-is-better-than-expected-how-to-try-it-for-free-before-you-subscribe\/#link={\">Grok 3<\/a>, was jailbroken, and the results aren&#8217;t pretty.&nbsp;<\/p>\n<p>On Tuesday, Adversa AI, a security and AI safety firm that regularly red-teams AI models, <a href=\"https:\/\/adversa.ai\/blog\/grok-3-jailbreak-and-ai-red-teaming\/\" target=\"_blank\" rel=\"noopener nofollow\" class=\"c-regularLink\">released a report<\/a> detailing its success in getting the Grok 3 Reasoning beta to share information it shouldn&#8217;t. Using three methods &#8212; linguistic, adversarial, and programming &#8212; the team got the model to reveal its system prompt, provide instructions for making a bomb, and offer gruesome methods for disposing of a body, among several other responses AI models are trained not to give.&nbsp;<\/p>\n<p><strong>Also: <a href=\"https:\/\/www.zdnet.com\/article\/if-musk-wants-ai-for-the-world-why-not-open-source-all-the-grok-models\/\">If Musk wants AI for the world, why not open-source all the Grok models?<\/a><\/strong><\/p>\n<p>During the announcement of the new model, xAI CEO Elon Musk <a href=\"https:\/\/www.zdnet.com\/article\/xais-grok-3-is-better-than-expected-how-to-try-it-for-free-before-you-subscribe\/\">claimed<\/a> it was &#8220;an order of magnitude more capable than Grok 2.&#8221; Adversa concurs in its report that the level of detail in Grok 3&#8217;s answers is &#8220;unlike in any previous reasoning model&#8221; &#8212; which, in this context, is rather concerning.&nbsp;<\/p>\n<p>In an email to ZDNET, Adversa CEO Alex Polyakov explained that what imperils security is the way Grok and, on occasion, DeepSeek, offer &#8220;executable&#8221; instructions.&nbsp;<\/p>\n<p><!----><\/p>\n<p>&#8220;It&#8217;s like the difference between &#8216;this is how a car engine works&#8217; and &#8216;here&#8217;s exactly how to build one from scratch,'&#8221; he added. &#8220;Typically, when you jailbreak a model with strong safeguards like OpenAI&#8217;s or Anthropic&#8217;s, you might get a response, but the details are often watered down &#8212; more of a vague outline than an actual blueprint.&#8221;<\/p>\n<p>Though Adversa admits its test wasn&#8217;t &#8220;exhaustive,&#8221; the report concludes that Grok 3&#8217;s safety and security guardrails are still &#8220;very weak,&#8221; noting &#8220;every jailbreak approach and every risk was successful.&#8221;<\/p>\n<p><strong>Also: <a href=\"https:\/\/www.zdnet.com\/article\/what-is-perplexity-deep-research-and-how-do-you-use-it\/\">What is Perplexity Deep Research, and how do you use it?<\/a><\/strong><\/p>\n<p>By design, Grok has fewer guardrails than competitors, a feature Musk himself has reveled in. (Grok&#8217;s <a href=\"https:\/\/x.ai\/blog\/grok\" target=\"_blank\" rel=\"noopener nofollow\" class=\"c-regularLink\">announcement<\/a> in 2023 noted the chatbot would &#8220;answer spicy questions that are rejected by most other AI systems.&#8221;) Pointing to the&nbsp;<a href=\"https:\/\/www.zdnet.com\/article\/how-apple-google-and-microsoft-can-save-us-from-ai-deepfakes\/\">misinformation<\/a> Grok spread during the 2024 election &#8212; which xAI&nbsp;<a href=\"https:\/\/apnews.com\/article\/election-2024-misinformation-x-twitter-elon-musk-4821523a795ba0dd04695c385c4b14d3\" target=\"_blank\" rel=\"noopener nofollow\" class=\"c-regularLink\">then updated the chatbot<\/a> to account for after being urged by election officials in five states &#8212; Northwestern&#8217;s Center for Advancing Safety of Machine Intelligence&nbsp;<a href=\"https:\/\/casmi.northwestern.edu\/news\/articles\/2024\/misinformation-at-scale-elon-musks-grok-and-the-battle-for-truth.html\" target=\"_blank\" rel=\"noopener nofollow\" class=\"c-regularLink\">reiterated in a statement<\/a>&nbsp;that &#8220;unlike Google and OpenAI, which have implemented strong guardrails around political queries, Grok was designed without such constraints.&#8221; <\/p>\n<p>Even Grok&#8217;s Aurora image generator does not have many guardrails or emphasize safety. Its initial release featured&nbsp;<a href=\"https:\/\/www.zdnet.com\/article\/all-x-users-can-now-access-grok-ai-chatbot-and-its-new-image-generator-for-free\/#link={\">sample generations that were rather dicey<\/a>, including hyperrealistic photos of former Vice President Kamala Harris that were used as election misinformation, and violent images of Donald Trump.&nbsp;<\/p>\n<p>The fact that Grok was trained on tweets perhaps exaggerates this lack of guardrails, considering Musk has dramatically reduced and even eliminated content moderation efforts on the platform since he purchased it in 2022. That quality of data combined with loose restrictions can produce much riskier query results.&nbsp;<\/p>\n<p><strong>Also: <a href=\"https:\/\/www.zdnet.com\/article\/us-sets-ai-safety-aside-in-favor-of-ai-dominance\/\">US sets AI safety aside in favor of &#8216;AI dominance&#8217;<\/a><\/strong><\/p>\n<p>The report comes amidst a seemingly endless list of safety and security concerns over Chinese startup&nbsp;<a href=\"https:\/\/www.zdnet.com\/article\/what-is-deepseek-ai-is-it-safe-heres-everything-you-need-to-know\/\">DeepSeek AI<\/a>&nbsp;and its models, which have also been <a href=\"https:\/\/www.zdnet.com\/article\/deepseeks-ai-model-proves-easy-to-jailbreak-and-worse\/\">easily jailbroken<\/a>. With the Trump administration steadily removing the little AI regulation already in place in the US, there are fewer external safeguards incentivizing AI companies to make their models as safe and secure as possible.&nbsp;<\/p>\n<div id=\"pinbox-574d70a3-6756-4b36-8486-e0d863da2c9b\" class=\"c-shortcodePinbox-carousel\">\n<div class=\"c-listingCarouselHorizontal\">\n<h4 class=\"c-sectionHeading\">Artificial Intelligence<\/h4>\n<p> <!----> <span class=\"c-listingCarouselHorizontal_loadingIndicator\"><\/span> <\/div>\n<\/div>\n<p>READ MORE <a href=\"https:\/\/www.zdnet.com\/article\/yikes-jailbroken-grok-3-can-be-made-to-say-and-reveal-just-about-anything\/\">HERE<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<p>A red team got xAI&#8217;s latest model to reveal its system prompt, provide instructions for making a bomb, and worse. Much worse.READ MORE HERE&#8230;<\/p>\n","protected":false},"author":2,"featured_media":0,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"colormag_page_layout":"default_layout","footnotes":""},"categories":[62],"tags":[],"class_list":["post-58201","post","type-post","status-publish","format-standard","hentry","category-zdnet-security"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v27.7 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>Yikes: Jailbroken Grok 3 can be made to say and reveal just about anything 2026 | ThreatsHub Cybersecurity News<\/title>\n<meta name=\"description\" content=\"ThreatsHub Cybersecurity News | ThreatsHub.org | Cloud Security &amp; Cyber Threats Analysis Hub. 100% Free OSINT Threat Intelligent and Cybersecurity News.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/www.threatshub.org\/blog\/yikes-jailbroken-grok-3-can-be-made-to-say-and-reveal-just-about-anything\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Yikes: Jailbroken Grok 3 can be made to say and reveal just about anything 2026 | ThreatsHub Cybersecurity News\" \/>\n<meta property=\"og:description\" content=\"ThreatsHub Cybersecurity News | ThreatsHub.org | Cloud Security &amp; Cyber Threats Analysis Hub. 100% Free OSINT Threat Intelligent and Cybersecurity News.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.threatshub.org\/blog\/yikes-jailbroken-grok-3-can-be-made-to-say-and-reveal-just-about-anything\/\" \/>\n<meta property=\"og:site_name\" content=\"ThreatsHub Cybersecurity News\" \/>\n<meta property=\"article:published_time\" content=\"2025-02-19T17:32:00+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/www.zdnet.com\/a\/img\/resize\/fb47548cd0afa75df9d0835c03d9d6c0e9ec9d0c\/2025\/02\/19\/bedbbafb-fcc1-43f7-a9e2-e0ab710f2a45\/gettyimages-1741475260.jpg?auto=webp&amp;width=1280\" \/>\n<meta name=\"author\" content=\"TH Author\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:creator\" content=\"@threatshub\" \/>\n<meta name=\"twitter:site\" content=\"@threatshub\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"TH Author\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"3 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\\\/\\\/www.threatshub.org\\\/blog\\\/yikes-jailbroken-grok-3-can-be-made-to-say-and-reveal-just-about-anything\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/www.threatshub.org\\\/blog\\\/yikes-jailbroken-grok-3-can-be-made-to-say-and-reveal-just-about-anything\\\/\"},\"author\":{\"name\":\"TH Author\",\"@id\":\"https:\\\/\\\/www.threatshub.org\\\/blog\\\/#\\\/schema\\\/person\\\/12e0a8671ff89a863584f193e7062476\"},\"headline\":\"Yikes: Jailbroken Grok 3 can be made to say and reveal just about anything\",\"datePublished\":\"2025-02-19T17:32:00+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/www.threatshub.org\\\/blog\\\/yikes-jailbroken-grok-3-can-be-made-to-say-and-reveal-just-about-anything\\\/\"},\"wordCount\":589,\"publisher\":{\"@id\":\"https:\\\/\\\/www.threatshub.org\\\/blog\\\/#organization\"},\"image\":{\"@id\":\"https:\\\/\\\/www.threatshub.org\\\/blog\\\/yikes-jailbroken-grok-3-can-be-made-to-say-and-reveal-just-about-anything\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/www.zdnet.com\\\/a\\\/img\\\/resize\\\/fb47548cd0afa75df9d0835c03d9d6c0e9ec9d0c\\\/2025\\\/02\\\/19\\\/bedbbafb-fcc1-43f7-a9e2-e0ab710f2a45\\\/gettyimages-1741475260.jpg?auto=webp&amp;width=1280\",\"articleSection\":[\"ZDNet | Security\"],\"inLanguage\":\"en-US\"},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/www.threatshub.org\\\/blog\\\/yikes-jailbroken-grok-3-can-be-made-to-say-and-reveal-just-about-anything\\\/\",\"url\":\"https:\\\/\\\/www.threatshub.org\\\/blog\\\/yikes-jailbroken-grok-3-can-be-made-to-say-and-reveal-just-about-anything\\\/\",\"name\":\"Yikes: Jailbroken Grok 3 can be made to say and reveal just about anything 2026 | ThreatsHub Cybersecurity News\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/www.threatshub.org\\\/blog\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/www.threatshub.org\\\/blog\\\/yikes-jailbroken-grok-3-can-be-made-to-say-and-reveal-just-about-anything\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/www.threatshub.org\\\/blog\\\/yikes-jailbroken-grok-3-can-be-made-to-say-and-reveal-just-about-anything\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/www.zdnet.com\\\/a\\\/img\\\/resize\\\/fb47548cd0afa75df9d0835c03d9d6c0e9ec9d0c\\\/2025\\\/02\\\/19\\\/bedbbafb-fcc1-43f7-a9e2-e0ab710f2a45\\\/gettyimages-1741475260.jpg?auto=webp&amp;width=1280\",\"datePublished\":\"2025-02-19T17:32:00+00:00\",\"description\":\"ThreatsHub Cybersecurity News | ThreatsHub.org | Cloud Security & Cyber Threats Analysis Hub. 100% Free OSINT Threat Intelligent and Cybersecurity News.\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/www.threatshub.org\\\/blog\\\/yikes-jailbroken-grok-3-can-be-made-to-say-and-reveal-just-about-anything\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/www.threatshub.org\\\/blog\\\/yikes-jailbroken-grok-3-can-be-made-to-say-and-reveal-just-about-anything\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/www.threatshub.org\\\/blog\\\/yikes-jailbroken-grok-3-can-be-made-to-say-and-reveal-just-about-anything\\\/#primaryimage\",\"url\":\"https:\\\/\\\/www.zdnet.com\\\/a\\\/img\\\/resize\\\/fb47548cd0afa75df9d0835c03d9d6c0e9ec9d0c\\\/2025\\\/02\\\/19\\\/bedbbafb-fcc1-43f7-a9e2-e0ab710f2a45\\\/gettyimages-1741475260.jpg?auto=webp&amp;width=1280\",\"contentUrl\":\"https:\\\/\\\/www.zdnet.com\\\/a\\\/img\\\/resize\\\/fb47548cd0afa75df9d0835c03d9d6c0e9ec9d0c\\\/2025\\\/02\\\/19\\\/bedbbafb-fcc1-43f7-a9e2-e0ab710f2a45\\\/gettyimages-1741475260.jpg?auto=webp&amp;width=1280\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/www.threatshub.org\\\/blog\\\/yikes-jailbroken-grok-3-can-be-made-to-say-and-reveal-just-about-anything\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/www.threatshub.org\\\/blog\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Yikes: Jailbroken Grok 3 can be made to say and reveal just about anything\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/www.threatshub.org\\\/blog\\\/#website\",\"url\":\"https:\\\/\\\/www.threatshub.org\\\/blog\\\/\",\"name\":\"ThreatsHub Cybersecurity News\",\"description\":\"%%focuskw%% Threat Intel \u2013 Threat Intel Services \u2013 CyberIntelligence \u2013 Cyber Threat Intelligence - Threat Intelligence Feeds - Threat Intelligence Reports - CyberSecurity Report \u2013 Cyber Security PDF \u2013 Cybersecurity Trends - Cloud Sandbox \u2013- Threat IntelligencePortal \u2013 Incident Response \u2013 Threat Hunting \u2013 IOC - Yara - Security Operations Center \u2013 SecurityOperation Center \u2013 Security SOC \u2013 SOC Services - Advanced Threat - Threat Detection - TargetedAttack \u2013 APT \u2013 Anti-APT \u2013 Advanced Protection \u2013 Cyber Security Services \u2013 Cybersecurity Services -Threat Intelligence Platform\",\"publisher\":{\"@id\":\"https:\\\/\\\/www.threatshub.org\\\/blog\\\/#organization\"},\"alternateName\":\"Threatshub.org\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/www.threatshub.org\\\/blog\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Organization\",\"@id\":\"https:\\\/\\\/www.threatshub.org\\\/blog\\\/#organization\",\"name\":\"ThreatsHub.org\",\"alternateName\":\"Threatshub.org\",\"url\":\"https:\\\/\\\/www.threatshub.org\\\/blog\\\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/www.threatshub.org\\\/blog\\\/#\\\/schema\\\/logo\\\/image\\\/\",\"url\":\"https:\\\/\\\/www.threatshub.org\\\/blog\\\/wp-content\\\/uploads\\\/2025\\\/05\\\/Threatshub_Favicon1.jpg\",\"contentUrl\":\"https:\\\/\\\/www.threatshub.org\\\/blog\\\/wp-content\\\/uploads\\\/2025\\\/05\\\/Threatshub_Favicon1.jpg\",\"width\":432,\"height\":435,\"caption\":\"ThreatsHub.org\"},\"image\":{\"@id\":\"https:\\\/\\\/www.threatshub.org\\\/blog\\\/#\\\/schema\\\/logo\\\/image\\\/\"},\"sameAs\":[\"https:\\\/\\\/x.com\\\/threatshub\"]},{\"@type\":\"Person\",\"@id\":\"https:\\\/\\\/www.threatshub.org\\\/blog\\\/#\\\/schema\\\/person\\\/12e0a8671ff89a863584f193e7062476\",\"name\":\"TH Author\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/066276f086d5155df79c850206a779ad368418a844da0182ce43f9cd5b506c3d?s=96&d=mm&r=g\",\"url\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/066276f086d5155df79c850206a779ad368418a844da0182ce43f9cd5b506c3d?s=96&d=mm&r=g\",\"contentUrl\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/066276f086d5155df79c850206a779ad368418a844da0182ce43f9cd5b506c3d?s=96&d=mm&r=g\",\"caption\":\"TH Author\"}}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Yikes: Jailbroken Grok 3 can be made to say and reveal just about anything 2026 | ThreatsHub Cybersecurity News","description":"ThreatsHub Cybersecurity News | ThreatsHub.org | Cloud Security & Cyber Threats Analysis Hub. 100% Free OSINT Threat Intelligent and Cybersecurity News.","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/www.threatshub.org\/blog\/yikes-jailbroken-grok-3-can-be-made-to-say-and-reveal-just-about-anything\/","og_locale":"en_US","og_type":"article","og_title":"Yikes: Jailbroken Grok 3 can be made to say and reveal just about anything 2026 | ThreatsHub Cybersecurity News","og_description":"ThreatsHub Cybersecurity News | ThreatsHub.org | Cloud Security & Cyber Threats Analysis Hub. 100% Free OSINT Threat Intelligent and Cybersecurity News.","og_url":"https:\/\/www.threatshub.org\/blog\/yikes-jailbroken-grok-3-can-be-made-to-say-and-reveal-just-about-anything\/","og_site_name":"ThreatsHub Cybersecurity News","article_published_time":"2025-02-19T17:32:00+00:00","og_image":[{"url":"https:\/\/www.zdnet.com\/a\/img\/resize\/fb47548cd0afa75df9d0835c03d9d6c0e9ec9d0c\/2025\/02\/19\/bedbbafb-fcc1-43f7-a9e2-e0ab710f2a45\/gettyimages-1741475260.jpg?auto=webp&amp;width=1280","type":"","width":"","height":""}],"author":"TH Author","twitter_card":"summary_large_image","twitter_creator":"@threatshub","twitter_site":"@threatshub","twitter_misc":{"Written by":"TH Author","Est. reading time":"3 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/www.threatshub.org\/blog\/yikes-jailbroken-grok-3-can-be-made-to-say-and-reveal-just-about-anything\/#article","isPartOf":{"@id":"https:\/\/www.threatshub.org\/blog\/yikes-jailbroken-grok-3-can-be-made-to-say-and-reveal-just-about-anything\/"},"author":{"name":"TH Author","@id":"https:\/\/www.threatshub.org\/blog\/#\/schema\/person\/12e0a8671ff89a863584f193e7062476"},"headline":"Yikes: Jailbroken Grok 3 can be made to say and reveal just about anything","datePublished":"2025-02-19T17:32:00+00:00","mainEntityOfPage":{"@id":"https:\/\/www.threatshub.org\/blog\/yikes-jailbroken-grok-3-can-be-made-to-say-and-reveal-just-about-anything\/"},"wordCount":589,"publisher":{"@id":"https:\/\/www.threatshub.org\/blog\/#organization"},"image":{"@id":"https:\/\/www.threatshub.org\/blog\/yikes-jailbroken-grok-3-can-be-made-to-say-and-reveal-just-about-anything\/#primaryimage"},"thumbnailUrl":"https:\/\/www.zdnet.com\/a\/img\/resize\/fb47548cd0afa75df9d0835c03d9d6c0e9ec9d0c\/2025\/02\/19\/bedbbafb-fcc1-43f7-a9e2-e0ab710f2a45\/gettyimages-1741475260.jpg?auto=webp&amp;width=1280","articleSection":["ZDNet | Security"],"inLanguage":"en-US"},{"@type":"WebPage","@id":"https:\/\/www.threatshub.org\/blog\/yikes-jailbroken-grok-3-can-be-made-to-say-and-reveal-just-about-anything\/","url":"https:\/\/www.threatshub.org\/blog\/yikes-jailbroken-grok-3-can-be-made-to-say-and-reveal-just-about-anything\/","name":"Yikes: Jailbroken Grok 3 can be made to say and reveal just about anything 2026 | ThreatsHub Cybersecurity News","isPartOf":{"@id":"https:\/\/www.threatshub.org\/blog\/#website"},"primaryImageOfPage":{"@id":"https:\/\/www.threatshub.org\/blog\/yikes-jailbroken-grok-3-can-be-made-to-say-and-reveal-just-about-anything\/#primaryimage"},"image":{"@id":"https:\/\/www.threatshub.org\/blog\/yikes-jailbroken-grok-3-can-be-made-to-say-and-reveal-just-about-anything\/#primaryimage"},"thumbnailUrl":"https:\/\/www.zdnet.com\/a\/img\/resize\/fb47548cd0afa75df9d0835c03d9d6c0e9ec9d0c\/2025\/02\/19\/bedbbafb-fcc1-43f7-a9e2-e0ab710f2a45\/gettyimages-1741475260.jpg?auto=webp&amp;width=1280","datePublished":"2025-02-19T17:32:00+00:00","description":"ThreatsHub Cybersecurity News | ThreatsHub.org | Cloud Security & Cyber Threats Analysis Hub. 100% Free OSINT Threat Intelligent and Cybersecurity News.","breadcrumb":{"@id":"https:\/\/www.threatshub.org\/blog\/yikes-jailbroken-grok-3-can-be-made-to-say-and-reveal-just-about-anything\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.threatshub.org\/blog\/yikes-jailbroken-grok-3-can-be-made-to-say-and-reveal-just-about-anything\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.threatshub.org\/blog\/yikes-jailbroken-grok-3-can-be-made-to-say-and-reveal-just-about-anything\/#primaryimage","url":"https:\/\/www.zdnet.com\/a\/img\/resize\/fb47548cd0afa75df9d0835c03d9d6c0e9ec9d0c\/2025\/02\/19\/bedbbafb-fcc1-43f7-a9e2-e0ab710f2a45\/gettyimages-1741475260.jpg?auto=webp&amp;width=1280","contentUrl":"https:\/\/www.zdnet.com\/a\/img\/resize\/fb47548cd0afa75df9d0835c03d9d6c0e9ec9d0c\/2025\/02\/19\/bedbbafb-fcc1-43f7-a9e2-e0ab710f2a45\/gettyimages-1741475260.jpg?auto=webp&amp;width=1280"},{"@type":"BreadcrumbList","@id":"https:\/\/www.threatshub.org\/blog\/yikes-jailbroken-grok-3-can-be-made-to-say-and-reveal-just-about-anything\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/www.threatshub.org\/blog\/"},{"@type":"ListItem","position":2,"name":"Yikes: Jailbroken Grok 3 can be made to say and reveal just about anything"}]},{"@type":"WebSite","@id":"https:\/\/www.threatshub.org\/blog\/#website","url":"https:\/\/www.threatshub.org\/blog\/","name":"ThreatsHub Cybersecurity News","description":"%%focuskw%% Threat Intel \u2013 Threat Intel Services \u2013 CyberIntelligence \u2013 Cyber Threat Intelligence - Threat Intelligence Feeds - Threat Intelligence Reports - CyberSecurity Report \u2013 Cyber Security PDF \u2013 Cybersecurity Trends - Cloud Sandbox \u2013- Threat IntelligencePortal \u2013 Incident Response \u2013 Threat Hunting \u2013 IOC - Yara - Security Operations Center \u2013 SecurityOperation Center \u2013 Security SOC \u2013 SOC Services - Advanced Threat - Threat Detection - TargetedAttack \u2013 APT \u2013 Anti-APT \u2013 Advanced Protection \u2013 Cyber Security Services \u2013 Cybersecurity Services -Threat Intelligence Platform","publisher":{"@id":"https:\/\/www.threatshub.org\/blog\/#organization"},"alternateName":"Threatshub.org","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.threatshub.org\/blog\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Organization","@id":"https:\/\/www.threatshub.org\/blog\/#organization","name":"ThreatsHub.org","alternateName":"Threatshub.org","url":"https:\/\/www.threatshub.org\/blog\/","logo":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.threatshub.org\/blog\/#\/schema\/logo\/image\/","url":"https:\/\/www.threatshub.org\/blog\/coredata\/uploads\/2025\/05\/Threatshub_Favicon1.jpg","contentUrl":"https:\/\/www.threatshub.org\/blog\/coredata\/uploads\/2025\/05\/Threatshub_Favicon1.jpg","width":432,"height":435,"caption":"ThreatsHub.org"},"image":{"@id":"https:\/\/www.threatshub.org\/blog\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/x.com\/threatshub"]},{"@type":"Person","@id":"https:\/\/www.threatshub.org\/blog\/#\/schema\/person\/12e0a8671ff89a863584f193e7062476","name":"TH Author","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/secure.gravatar.com\/avatar\/066276f086d5155df79c850206a779ad368418a844da0182ce43f9cd5b506c3d?s=96&d=mm&r=g","url":"https:\/\/secure.gravatar.com\/avatar\/066276f086d5155df79c850206a779ad368418a844da0182ce43f9cd5b506c3d?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/066276f086d5155df79c850206a779ad368418a844da0182ce43f9cd5b506c3d?s=96&d=mm&r=g","caption":"TH Author"}}]}},"_links":{"self":[{"href":"https:\/\/www.threatshub.org\/blog\/wp-json\/wp\/v2\/posts\/58201","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.threatshub.org\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.threatshub.org\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.threatshub.org\/blog\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.threatshub.org\/blog\/wp-json\/wp\/v2\/comments?post=58201"}],"version-history":[{"count":0,"href":"https:\/\/www.threatshub.org\/blog\/wp-json\/wp\/v2\/posts\/58201\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.threatshub.org\/blog\/wp-json\/wp\/v2\/media?parent=58201"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.threatshub.org\/blog\/wp-json\/wp\/v2\/categories?post=58201"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.threatshub.org\/blog\/wp-json\/wp\/v2\/tags?post=58201"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}